© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 4698
    Prev
    Next
    INDEX
    Explanations

    text related to on/off switches

    oai_token-act-pair · gemini-2.0-flash

    off

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    upon
    -1.04
    out
    -0.96
    up
    -0.93
    off
    -0.88
    OUT
    -0.84
    about
    -0.80
    für
    -0.79
    of
    -0.78
    UP
    -0.75
    over
    -0.73
    POSITIVE LOGITS
     out
    0.80
     away
    0.79
     up
    0.75
     off
    0.75
     over
    0.71
    +#+#
    0.69
     ahead
    0.65
     outside
    0.61
     on
    0.61
     down
    0.59
    Activations Density 3.876%

    No Known Activations